Symbolic Artificial Intelligence
Mostrando 1-8 de 8 artigos, teses e dissertações.
-
1. Aplicações de técnicas de inteligência artificial à comunicação alternativa e aumentativa
A maior parte da população mundial se comunica de forma multimodal (fala, gestos, expressões faciais, etc.). Na medida em que algum destes modos falta, a pessoa afetada encontra dificuldades para manifestar suas idéias e pensamentos. Este trabalho é destinado a pessoas com dificuldades severas de fala e graves danos, tamb6m, na parte motora, o que as im
Publicado em: 2010
-
2. Um modelo de extração de propriedades de textos usando pensamento narrativo e paradigmático. / A model of textsproperties extraction using narrative and paradigmatic thinking.
This work seeks to understand how man formulates his thoughts and use them to act in the world. It is not our purpose to exhaust this subject, but to discuss it and present a model of how this process might possibly occur. For this we made a new lecture of the thinking modes studied by the psychologist Jerome Bruner in the 1980s: narrative thinking and parad
Publicado em: 2007
-
3. Exploração de relações entre técnicas simbólicas e conexionistas da inteligência computacional. / Relations exploration between symbolic and connectionist techniques of computacional intelligence.
This work consists of a contribution to the area of Computational Intelligence, relating to some of its main techniques: Fuzzy Computing and Neural Computing. These techniques are being used to solve problems that are too complex for traditional algorithmic approach or mathematical modeling. However, these problems are solved easly with the apparatus that co
Publicado em: 2006
-
4. NLForSpec: Uma Ferramenta para GeraÃÃo de EspecificaÃÃes Formais a partir de Casos de Teste em Linguagem Natural
This work describes the NLForSpec, a Natural Language Processing tool to translate software test cases descriptions in English into a formal representation. NLForSpec is part of a larger project (CIn-Motorola BTC Test Research Project), which aims to automate test case generation, selection and evaluation for mobile phone applications. One of the projects ma
Publicado em: 2006
-
5. SpecNL: Uma ferramenta para gerar descriÃÃes em linguagem natural a partir de especificaÃÃes de casos de teste
Software Testing is an important task in the software development process. However, this task is very expensive. Studies suggest that Software Testing takes up to 50% of the total cost of software development. In order to automate and optimize the testing activities, several tools have been applied to aid the testing process, ranging from test generation to
Publicado em: 2006
-
6. Classificador simbÃlico baseado em regiÃes de tipo casca convexa
On the recent advancement from the information sciences technologies, deferent techniques are introduced to synthesize, analyze and extract information knowledge stored in huge databases. The symbolic data analysis (SDA) is a domain in the area of automatic knowledge discovery (KDD), related with multivariate data analysis, pattern recognition, artificial in
Publicado em: 2005
-
7. Desenvolvimento de uma plataforma hÃbrida para descoberta de conhecimento em bases de dados
Artificial Neural Networks (ANN) have successfully been used in tasks as the mapping of complex functions and pattern recognition. This success is due to the ANN ability to make calculations of complicated and undetermined data, learn from examples, generalize the learned information, extract patterns and discover tendencies. Despite these advantages, it is
Publicado em: 2004
-
8. Um ambiente para avaliação de algoritmos de aprendizado de máquina simbólico utilizando exemplos. / An environment to evaluate machine learning algorithms.
A learning system is a computer program that makes decisions based on the accumulative experience contained in successfully solved cases. The classification rules induced by a learning system are judged by two criteria: their classification error on an independent test set and their complexity. Practical learning systems have been developed using different p
Publicado em: 1997